Parallel Image Processing: Taking Grayscale Conversion Using OpenMP as an Example

In recent years, the widespread adoption of parallel computing, especially in multi-core processors and high-performance computing environments, ushered in a new era of efficiency and speed. This trend was particularly noteworthy in the field of image processing, which witnessed significant advancements. This parallel computing project explored the field of parallel image processing, with a focus on the grayscale conversion of colorful images. Our approach involved integrating OpenMP into our framework for parallelization to execute a critical image processing task: grayscale conversion. By using OpenMP, we strategically enhanced the overall performance of the conversion process by distributing the workload across multiple threads. The primary objectives of our project revolved around optimizing computation time and improving overall efficiency, particularly in the task of grayscale conversion of colorful images. Utilizing OpenMP for concurrent processing across multiple cores significantly reduced execution times through the effective distribution of tasks among these cores. The speedup values for various image sizes highlighted the efficacy of parallel processing, especially for large images. However, a detailed examination revealed a potential decline in parallelization efficiency with an increasing number of cores. This underscored the importance of a carefully optimized parallelization strategy, considering factors like load balancing and minimizing communication overhead. Despite challenges, the overall scalability and efficiency achieved with parallel image processing underscored OpenMP’s effectiveness in accelerating image manipulation tasks.

Dynamic Performance of High Speed Solenoid Valve with Parallel Coils

The methods of improving the dynamic performance of high speed on/off solenoid valve include increasing the magnetic force of armature and the slew rate of coil current, decreasing the mass and stroke of moving parts. The increase of magnetic force usually leads to the decrease of current slew rate, which could increase the delay time of the dynamic response of solenoid valve. Using a high voltage to drive coil can solve this contradiction, but a high driving voltage can also lead to more cost and a decrease of safety and reliability. In this paper, a new scheme of parallel coils is investigated, in which the single coil of solenoid is replaced by parallel coils with same ampere turns. Based on the mathematic model of high speed solenoid valve, the theoretical formula for the delay time of solenoid valve is deduced. Both the theoretical analysis and the dynamic simulation show that the effect of dividing a single coil into N parallel sub-coils is close to that of driving the single coil with N times of the original driving voltage as far as the delay time of solenoid valve is concerned. A specific test bench is designed to measure the dynamic performance of high speed on/off solenoid valve. The experimental results also prove that both the delay time and switching time of the solenoid valves can be decreased greatly by adopting the parallel coil scheme. This research presents a simple and practical method to improve the dynamic performance of high speed on/off solenoid valve.

Development of a Novel Parallel-spool Pilot Operated High-pressure Solenoid Valve with High Flow Rate and High Speed

High-pressure solenoid valve with high flow rate and high speed is a key component in an underwater driving system.However,traditional single spool pilot operated valve cannot meet the demands of both high flow rate and high speed simultaneously.A new structure for a high pressure solenoid valve is needed to meet the demand of the underwater driving system.A novel parallel-spool pilot operated high-pressure solenoid valve is proposed to overcome the drawback of the current single spool design.Mathematical models of the opening process and flow rate of the valve are established.Opening response time of the valve is subdivided into 4 parts to analyze the properties of the opening response.Corresponding formulas to solve 4 parts of the response time are derived.Key factors that influence the opening response time are analyzed.According to the mathematical model of the valve,a simulation of the opening process is carried out by MATLAB.Parameters are chosen based on theoretical analysis to design the test prototype of the new type of valve.Opening response time of the designed valve is tested by verifying response of the current in the coil and displacement of the main valve spool.The experimental results are in agreement with the simulated results,therefore the validity of the theoretical analysis is verified.Experimental opening response time of the valve is 48.3 ms at working pressure of 10 MPa.The flow capacity test shows that the largest effective area is 126 mm2 and the largest air flow rate is 2320 L/s.According to the result of the load driving test,the valve can meet the demands of the driving system.The proposed valve with parallel spools provides a new method for the design of a high-pressure valve with fast response and large flow rate.

Dynamic Analysis of High-Speed Boat Motion Simulator by a Novel 3-DoF Parallel Mechanism with Prismatic Actuators Based on Seakeeping Trial

In this study,we focused on a novel parallel mechanism for utilizing the motion simulator of a high-speed boat(HSB).First,we expressed the real behavior of the HSB based on a seakeeping trial.For this purpose,we recorded the motion parameters of the HSB by gyroscope and accelerometer sensors,while using a special data acquisition technique.Additionally,a Chebychev highpass filter was applied as a noise filter to the accelerometer sensor.Then,a novel 3 degrees of freedom(DoF)parallel mechanism(1T2R)with prismatic actuators is proposed and analyses were performed on its inverse kinematics,velocity,and acceleration.Finally,the inverse dynamic analysis is presented by the principle of virtual work,and the validation of the analytical equations was compared by the ADAMS simulation software package.Additionally,according to the recorded experimental data of the HSB,the feasibility of the proposed novel parallel mechanism motion simulator of the HSB,as well as the necessity of using of the washout filters,was explored.

New Family of 3-DOF UP-Equivalent Parallel Mechanisms with High Rotational Capability

Parallel mechanisms(PMs) having the same motion characteristic with a UP kinematic chain(U denotes a universal joint, and P denotes a prismatic joint) are called UP-equivalent PMs. They can be used in many applications, such as machining and milling. However, the existing UP-equivalent PMs suffer from the disadvantages of strict assembly requirements and limited rotational capability. Type synthesis of UP-equivalent PMs with high rotational capability is presented.The special 2 R1 T motion is briefly discussed and the fact that the parallel module of the Exechon robot is not a UP-equivalent PM is disclosed. Using the Lie group theory, the kinematic bonds of limb chains and their mechanical generators are presented. Structural conditions for constructing such UP-equivalent PMs are proposed,which results in numerous new architectures of UP-equivalent PMs. The high rotational capability of the synthesized mechanisms is illustrated by an example. The advantages of no strict assembly requirements and high rotational capability of the newly developed PMs will facilitate their applications in the manufacturing industry.

Analysis of stress and natural frequencies of high-speed spatial parallel mechanism

In order to grasp the dynamic behaviors of 4-UPS-UPU high-speed spatial parallel mechanism, the stress of driving limbs and natural frequencies of parallel mechanism were investigated. Based on flexible multi-body dynamics theory, the dynamics model of 4-UPS-UPU high-speed spatial parallel mechanism without considering geometric nonlinearity was derived. The stress of driving limbs and natural frequencies of 4-UPS-UPU parallel mechanism with specific parameters were analyzed. The relationship between the basic parameters of parallel mechanism and its dynamic behaviors, such as stress of driving limbs and natural frequencies of parallel mechanism, were discussed. The numerical simulation results show that the stress and natural frequencies are relatively sensitive to the section parameters of driving limbs, the characteristic parameters of material on driving limbs, and the mass of moving platform. The researches can provide important theoretical base of the analysis of dynamic behaviors and optimal design for high-speed spatial parallel mechanism.

Massive Molecular Parallel Evolution of the HSP90AA1 Gene between High-elevation Anurans

HSP90 AA1 is part of the heat shock protein 90 gene family and has important functions against heat stress. We report a case of molecular level parallel evolution of the HSP90 AA1 gene in high elevation amphibians. HSP90 AA1 gene sequences of four high-elevation anurans, Bufo gargarizans, Nanorana parkeri, Rana kukunoris, and Scutiger boulengeri, were compared along with five of their low-elevation relatives. A total of 16 amino-acid sites were identified as parallel evolution between N. parkeri and R. kukunoris. We generated both model based（Zhang and Kumar＇s test） and empirical data based（parallel/divergence plotting） null distributions for non-parallel evolution, and both methods clearly determined that the observed number of parallel substitutions were significantly more than the null expectation. Furthermore, on the HSP90 AA1 gene tree, N. parkeri and R. kukunoris formed a strongly supported clade that was away from their respective relatives. This study provides a clear case of molecular parallel evolution, which may have significant implications in understanding the genetic mechanisms of high-elevation adaptation.

基于新型CD单元的两相交错并联高增益Boost变换器

为减少基于电容-二极管(CD)升压单元的两相交错并联高增益Boost变换器的CD单元数量,提升变换器电压增益,提出一种最后两级CD单元电容并联充电、串联供电的新型两相交错Boost变换器拓扑结构,进一步发挥CD单元的升压能力。分析新型3CD、4CD两相交错并联Boost变换器的拓扑演化过程,提出新型NCD两相交错并联Boost变换器的拓扑演化规律。以新型4CD两相交错并联Boost变换器为例,分析变换器工作原理,以及电感、电容寄生电阻对变换器电压增益的影响。最后在StarSim硬件在环实验平台搭建1 kW的新型4CD单元交错并联Boost变换器,验证该文所提拓扑的正确性。

多线并行轨道电路电容耦合干扰机理研究

高速铁路车站并行股道多,应用场景复杂,在三线并行情况下,中间股道易受两旁线路的电磁干扰影响。当2条线路均与中间股道同向时,中间股道所受电容耦合干扰为2条线路干扰之和,且邻线耦合电容越大,干扰亦越强。为减少多线并行邻线间的电容耦合干扰,可采取改变线路相对布局、采用屏蔽等设计措施,确保高速铁路车站轨道电路工作的稳定性和可靠性。

申威26010众核处理器上Winograd卷积算法的研究与优化

卷积作为深度学习中被频繁使用的关键部分,其并行算法的研究已成为高性能计算领域中的热门话题.随着我国自主研发的申威26010众核处理器在人工智能领域的快速发展,对面向该处理器的高性能并行卷积算法提出了迫切的需求.针对申威26010处理器的架构特征以及Winograd卷积算法的计算特性,提出了一种高性能并行卷积算法——融合Winograd卷积算法.该算法不同于依赖官方GEMM(general matrix multiplication)库接口的传统Winograd卷积算法,定制的矩阵乘实现使得该算法的执行过程变得可见,且能够更好地适应现实中常见卷积运算.整个算法由输入的Winograd变换、卷积核的Winograd变换、核心运算和输出的Winograd逆变换4部分构成,这4个部分并不是单独执行而是融合到一起执行.通过实时地为核心运算提供需要的变换后数据,并将计算结果及时地逆变换得到最终的输出数据,提高了算法执行过程中的数据局部性,极大地降低了整体的访存开销.同时,为该算法设计了合并的Winograd变换模式、DMA(direct memory access)双缓冲、片上存储的强化使用、输出数据块的弹性处理以及指令重排等优化方案.最终的实验结果表明,在VGG网络模型的总体卷积测试中,该算法性能是传统Winograd卷积算法的7.8倍.同时,抽取典型卷积神经网络模型中的卷积进行测试,融合Winograd卷积算法能够在所有的卷积场景中发挥明显高于传统Winograd卷积算法的性能.其中,最大能够发挥申威26010处理器峰值性能的116.21%,平均能够发挥峰值性能的93.14%.

基于345-修正梯形运动规律的4-RR(SS)_(2)并联机器人运动轨迹规划

研究了一种新型四自由度高速并联机器人运动轨迹规划方法。该机器人采用单动平台结构以减轻末端平台质量,提升机器人加减速性能。建立机器人机构运动学逆解模型,通过融合345多项式和梯形运动规律的优点,构造一种可兼顾运动时长和运动平稳性的345-修正梯形运动规律。在此基础上,通过插补叠加轨迹过渡传统门形轨迹的直角部分,并统筹考虑总运动时长最短以及角加速度峰值最小为目标完成插补叠加时机的优选,最后在样机上开展运动频次试验。试验结果显示,采用优化后的运动规律和轨迹样机运动频次可提升至218次/min,工作效率较传统Adept门形轨迹提高55.7%。

面向GPU架构的CCFD-KSSolver组件设计和实现

【应用背景】在如计算流体力学和材料科学等高性能应用领域中,大型稀疏线性方程的求解直接影响高性能应用的效率与精度。异构众核已成为现代超算系统体系结构的重要特征和发展趋势。【方法】本文面向CPU+GPU异构超算系统设计并实现了线性解法器组件CCFD-KSSolver。该组件针对异构体系结构特征,实现了针对多物理场块结构矩阵的Krylov子空间解法器和多种典型预处理方法,采用了如计算通信重叠、GPU访存优化、CPUGPU协同计算等优化技术提升CCFD-KSSolver的计算效率。【结果】顶盖驱动流的实验表明,当子区域数目为8时,Block-ISAI相比于CPU和cuSPARSE的子区域求解器分别取得20.09倍和3.34倍的加速比,且具有更好的扩展性;对于百万阶规模的矩阵,应用3种子区域求解器的KSSolver在8个GPU上的并行效率分别为83.8%、55.7%、87.4%。【结论】本文选择具有块结构的经典多物理中的应用对解法器及预处理软构件进行测试,证明其稳定高效性,有力支撑了以流体力学数值模拟为代表的高性能计算与应用在异构系统上的开展。

低冗余高可靠模块化输入并联输出串联电源系统及其控制方法

为了使输入并联输出串联电源系统同时具备模块级和系统级冗余能力,提出低冗余高可靠超宽电压范围电路结构及其控制方法。基于两级式电路和多模块串并联实现电源系统超宽电压输出,通过模块级部分子电路冗余设计,实现模块级和系统级N+X双重冗余,使得功率模块部分失效或多个模块全部失效时系统仍具有全电压、全功率输出能力。进一步提出模块化电源系统的分布-集中混合式控制策略,分布式自主控制保证了模块间应力均衡、并使得输出电压在目标值范围内,集中控制确保总输出电压精度。该文详细分析所提电路结构及其控制策略的原理、特性和实现方案,并通过0~1000 V/50 kW输出电源系统实验,验证了所提方案的有效性。

指控中心任务软件集中管控系统研究与关键技术

随着武器航天试验任务的增多,指控中心对任务软件快速部署、多任务并行的需求愈发迫切。设计了基于B/S架构的指控中心任务软件集中管控系统,实现了任务软件配置与监控的一体化管理;通过基于DBus与Kafka结合的数据传输机制,打通了任务软件与系统前后端数据高效交互链路;最后,重点分析了任务软件自动化部署技术、多任务并行技术、高速数据分级处理技术以及任务数据高效存储技术。

先进中子学程序SCAP-N混合并行方法

为提高先进中子学程序SCAP-N的计算效率,提出并实现了1种MPI/OpenMP混合并行方案。采用MPI分布式并行模式,实现各分层2维堆芯计算间的并行及3维堆芯pin-by-pin输运计算的粗粒度区域分解并行。采用OpenMP共享存储式并行模式,实现分层2维堆芯内部非均匀输运计算的并行及3维堆芯pin-by-pin输运计算各MPI分区内部的细粒度并行。数值结果表明,该混合并行方法可有效实现SCAP-N程序的并行化,显著缩短程序计算时间,减少堆芯高精度中子输运计算区域分解数目,缓解源迭代格式退化,提高程序计算稳定性和收敛效率。

溶解性有机质与铅、砷相互作用研究

为研究天然水体中有机质与砷(As)、铅(Pb)相互作用,文章以标准溶解性有机质(标准DOM)为研究对象,利用光谱、超高分辨率质谱分析、平行因子分析法等方法进行分析。结果表明:(1)与类富里酸和腐殖质相比,类蛋白质酪氨酸类与As、Pb表现出更高结合能力。(2)超高分辨率质谱检测结果显示,重金属能够改变标准DOM原有特性,使得有机质发生转变,如氨基糖类组分减少,类单宁组分增加,CHO相对丰度减少,其他杂原子相对丰度增加。(3)DOM-As显示紫外特征参数a254和荧光特征参数HIX具有强正相关性,通过超高分辨质谱仪获得的氨基糖组分、CHO与紫外特征参数a254、a260、a280、荧光特征参数HIX均具有正相关性,荧光组分C1和质谱获得的不饱和烃类组分具有正相关性。研究结果可为定量评估水体中有机质-重金属相互作用机理提供理论支撑,从而减少重金属等各种污染物的环境行为。

基于三级式可扩展多模块并联架构的低压大电流高距径比无线电能传输系统

在低压大电流高距径比磁谐振式无线供电场合,由于传输线圈间的耦合系数很小,因此功率器件和谐振元件的电流很大,导致系统损耗大,难以优化设计。为此,文中提出一种三级式可扩展多模块并联无线电能传输系统架构,利用基波分析法对双模块并联系统建模并分析其传输特性。为提升系统效率,对比3种输出级结构及其控制策略并遴选出一种最优拓扑。进一步地,提出线圈级具体参数设计方法以减小电压电流应力并实现输入级软开关。最后搭建一台距径比为1(30 cm/30 cm)的1 kW原理样机验证理论分析,对比3种不同输出级拓扑的性能。实验结果表明,系统最高效率可达75.2%。

多逆变器模块并联驱动的大功率无线电能传输系统研究

针对传统单个逆变器驱动的无线电能传输(wireless power transfer,WPT)系统输出功率有限的问题,提出了一种多逆变器模块并联驱动的大功率WPT系统,并对多逆变器模块并联的拓扑结构和各模块间的环流进行了分析。为了解决逆变器并联时产生的环流问题,提出了基于主从策略的相位同步控制方法,通过从逆变器输出电压和发送端电流相位差同步于主逆变器输出电压和发送端电流相位差实现逆变器模块间的相位差补偿。研制了三个逆变器模块并联驱动的WPT系统样机,实验结果表明,在500 V直流输入时,负载端获得功率约为20 kW,传输效率达94%,且各逆变器输出电压相位实现同步,证明了相位同步控制方法的有效性。

异构并行的高阶散射特征线方法及其在临界实验装置模拟中的应用

在临界实验装置的物理计算中,由于较厚水反射层的存在,中子各向异性散射会对计算结果有重要影响。基于P1各向异性散射特征线方法(MOC),开发了能够处理各向异性散射的特征线输运计算程序,并实现了高阶散射特征线输运计算的高性能异构并行。为确认程序对临界实验装置的物理计算精度,本文选取LCT011临界实验基准进行堆芯物理计算,并与蒙特卡罗程序进行对比验证。各向异性源使得计算量与内存消耗均有显著增加,给异构系统带来较大的显存负担,因此本文进而对高阶散射输运求解器进行性能分析。数值结果表明:在高阶散射计算条件下,程序可达到蒙特卡罗程序的同等精度,且具有较高的计算效率。

高速通信系统中并行CRC计算及电路实现

针对高位宽数据情况下的循环冗余校验码(Cyclic Redundancy Code, CRC)电路计算工作频率较低以及资源占用过多的问题,设计并实现了一种并行CRC计算方法。该方法将CRC计算拆分为数据CRC计算和余数CRC计算两个部分,余数CRC计算由多个余数CRC计算模块级联完成,数据CRC计算模块由固定逻辑表达式实现,对二者计算结果做模二加法即得到CRC计算结果。根据数据长度选择相应的数据CRC计算模块和余数CRC计算模块的组合,以适应高位宽可变数据长度的CRC计算。以100 Gbps远程直接数据存取(Remote Direct Memory Access, RDMA)通信系统中的1 024 bits数据位宽CRC-32的计算为例,在VCU118开发板上实现了该算法的硬件电路。实验结果表明,所提设计仅使用4 760个查找表和2 658个触发器,整个系统带宽最高可达97.85 Gbps,最高工作频率可达326 MHz。与其他相关方法相比,提出的方法具有较高的工作频率且资源占用较少。